Historical districts contain spatial units with markedly different local microclimates, yet the temporal dynamics of their thermal-humidity environments and their associations with surrounding environmental conditions remain insufficiently resolved. This study examined three analytical settings in the Ciqikou Historical District, Chongqing: an Alley, the Main Street, and a Square. Using daytime multi-variable data collected on 4 August 2026, we integrated the temperature-humidity index (THI), an exact bivariate Shapley decomposition, and an XGBoost-SHAP framework to characterize thermal-humidity states and nonlinear environmental associations. Main Street and Square data were obtained from valid field measurements. Because the original Alley observations were lost owing to equipment failure, a stochastic reconstruction was generated within contemporaneous observational ranges and alley-specific environmental constraints; Alley results are therefore used only for exploratory comparison. Mean air temperature and THI were highest on Main Street (32.81 °C and 28.46 °C), followed by the Square (32.01 °C and 28.04 °C); the reconstructed Alley series yielded 31.16 °C and 27.73 °C, respectively. Exact Shapley decomposition showed that temperature accounted for 71.70–74.20% of the absolute contribution across the three analytical series, while the directions of the temperature and humidity contributions changed over time. These contribution shares depend on a common reference derived from both measured and reconstructed series and are not estimates based exclusively on field observations. Under grouped blocked cross-validation, out-of-fold R2 values were 0.80 for Main Street and 0.73 for Square, compared with 0.57 for the reconstructed Alley series. SHAP analysis indicated setting-specific predictive association structures and nonlinear responses. The high importance assigned to atmospheric pressure more plausibly reflects background meteorological and temporal covariation within the monitoring window than a direct causal effect. Overall, the results reveal pronounced context dependence in historical-district microclimates and underscore the importance of data provenance, temporal dependence, and explicit limits on model interpretation in short-duration field studies.
- Open Access
- Article
Microclimatic Heterogeneity and Nonlinear Environmental Associations Across Contrasting Spaces in a Historical District: An Exploratory THI–XGBoost–SHAP Framework
- Xuetong Song 1,2,
- Zhonghai Wang 1,2,*,
- Shaopeng Song 1,2,
- Zhenjiang Tian 3,*
Author Information
Received: 25 Aug 2026 | Revised: 29 Sep 2026 | Accepted: 12 Oct 2026 | Published: 22 Oct 2026
Abstract
Keywords
historical district | microclimate | XGBoost-SHAP | spatial heterogeneity | thermal environment
References
- 1.
Tuholske, C.; Caylor, K.; Funk, C.; et al. Global urban population exposure to extreme heat. Proc. Natl. Acad. Sci. USA 2021, 118, e2024792118. https://doi.org/10.1073/pnas.2024792118.
- 2.
Li, H.; Li, Y.; Wang, T.; et al. Quantifying 3D building form effects on urban land surface temperature and modeling seasonal correlation patterns. Build. Environ. 2021, 204, 108132. https://doi.org/10.1016/j.buildenv.2021.108132.
- 3.
Yu, J.; Hu, Q.; Li, J. Combining visual intelligence and social-physical urban features facilitates fine-scale seasonality characterization of urban thermal environments. Build. Environ. 2024, 266, 112088. https://doi.org/10.1016/j.buildenv.2024.112088.
- 4.
Ma, X.; Leung, T.M.; Chau, C.K.; et al. Analyzing the influence of urban morphological features on pedestrian thermal comfort. Urban Clim. 2022, 44, 101192. https://doi.org/10.1016/j.uclim.2022.101192.
- 5.
Li, Y.; Huang, N.; He, J. Analytical evaluation of thermal comfort in the pedestrian environment using pedestrian shade space distribution. Urban Clim. 2023, 51, 101665. https://doi.org/10.1016/j.uclim.2023.101665.
- 6.
Qi, L.; Li, T.; Chang, B.; et al. Research on Thermal Comfort Evaluation and Optimization of Green Space in Beijing Dashilar Historic District. Buildings 2024, 14, 3121. https://doi.org/10.3390/buildings14103121.
- 7.
Zheng, J.; Ou, Z.; Xiang, Y.; et al. How can street interface morphology effect pedestrian thermal comfort: A case study of the old town of Changsha, China. Urban Clim. 2025, 60, 102341. https://doi.org/10.1016/j.uclim.2025.102341.
- 8.
Cheng, R.; Wang, S.; Gao, W.; et al. Evaluation of courtyard outdoor thermal comfort: A case study of Qingdao Riyuan historic district in hot summer. Case Stud. Therm. Eng. 2025, 74, 106804. https://doi.org/10.1016/j.csite.2025.106804.
- 9.
Behzad, Z.; Guilandoust, A. Enhancing outdoor thermal comfort in a historic site in a hot dry climate (Case study: Naghsh-e-Jahan Square, Isfahan). Sustain. Cities Soc. 2024, 102, 105209. https://doi.org/10.1016/j.scs.2024.105209.
- 10.
Lai, B.; Fu, J.M.; Guo, C.K.; et al. Street Geometry Factors Influencing Outdoor Pedestrian Thermal Comfort in a Historic District. Buildings 2025, 15, 613. https://doi.org/10.3390/buildings15040613.
- 11.
Cherchi, G.; Santus, A.; Fiorino, D.R.; et al. Microclimate Assessment and Outdoor Human Comfort Enhancement of a Historic Village in Sardinia, Italy. Urban Plan. 2025, 10, 10708. https://doi.org/10.17645/up.10708.
- 12.
Wang, Y.; Liu, X.; Xie, R.; et al. Thermal comfort and urban microclimate response: A new thermal environment assessment model for waterfront spaces in historic ancient towns. Energy Build. 2025, 331, 115393. https://doi.org/10.1016/j.enbuild.2025.115393.
- 13.
Rezaie, P.; Lopez-Cabeza, V.P.; Sola-Caraballo, J.; et al. Cooling Heritage Scenarios: Transforming Historic Squares for Thermal Comfort. Buildings 2025, 15, 564. https://doi.org/10.3390/buildings15040564.
- 14.
Yin, S.; Wang, F.; Xiao, Y.; et al. Comparing cooling efficiency of shading strategies for pedestrian thermal comfort in street canyons of traditional shophouse neighbourhoods in Guangzhou, China. Urban Clim. 2022, 43, 101165. https://doi.org/10.1016/j.uclim.2022.101165.
- 15.
Haeri, T.; Hassan, N.; Ghaffarianhoseini, A. Evaluation of microclimate mitigation strategies in a heterogenous street canyon in Kuala Lumpur from outdoor thermal comfort perspective using Envi-met. Urban Clim. 2023, 52, 101719. https://doi.org/10.1016/j.uclim.2023.101719.
- 16.
Yang, Y.; Lee, X. Contributions of temperature and humidity to intra-city variations in humid heat. Urban Clim. 2024, 58, 102201. https://doi.org/10.1016/j.uclim.2024.102201.
- 17.
Ioannou, L.G.; Mantzios, K.; Tsoutsoubi, L.; et al. Indicators to assess physiological heat strain—Part 1: Systematic review. Temperature 2022, 9, 227–262. https://doi.org/10.1080/23328940.2022.2037376.
- 18.
Ji, Y.; Song, J.; Shen, P. A review of studies and modelling of solar radiation on human thermal comfort in outdoor environment. Build. Environ. 2022, 214, 108891. https://doi.org/10.1016/j.buildenv.2022.108891.
- 19.
Mahdavinejad, M.; Shaeri, J.; Nezami, A.; et al. Comparing universal thermal climate index (UTCI) with selected thermal indices to evaluate outdoor thermal comfort in traditional courtyards with BWh climate. Urban Clim. 2024, 54, 101839. https://doi.org/10.1016/j.uclim.2024.101839.
- 20.
Shapley, L.S. A Value for n-Person Games. In Contributions to the Theory of Games (AM-28), Volume II; Princeton University Press: Princeton, NJ, USA, 1953; pp. 307–318. https://doi.org/10.1515/9781400881970-018.
- 21.
Roy, T.B.; Middey, A.; Krupadam, R.J. Unveiling the microclimate: A comprehensive review of tools, techniques, and future directions for sustainable cities. Build. Environ. 2025, 274, 112726. https://doi.org/10.1016/j.buildenv.2025.112726.
- 22.
Kousis, I.; Pigliautile, I.; Pisello, A.L. Intra-urban microclimate investigation in urban heat island through a novel mobile monitoring system. Sci. Rep. 2021, 11, 9732. https://doi.org/10.1038/s41598-021-88344-y.
- 23.
Ahmad, M.; Panyametheekul, S.; Thaveevong, P.; et al. Long-term monitoring of PM2.5 and PM10: Implications for air quality and public health in urban Bangkok, Thailand. Environ. Chall. 2025, 21, 101312. https://doi.org/10.1016/j.envc.2025.101312.
- 24.
Samad, N.; Farnaghi, M.; Ostermann, F.O.; et al. A systematic literature review of machine learning and deep learning for urban heat island modelling. Discov. Cities 2026, 3, 43. https://doi.org/10.1007/s44327-026-00223-1.
- 25.
He, J.; Shi, Y.; Xu, L.; et al. Exploring the scale effect of urban thermal environment through XGBoost model. Sustain. Cities Soc. 2024, 114, 105763. https://doi.org/10.1016/j.scs.2024.105763.
- 26.
Chen, T.; Guestrin, C. XGBoost. In Proceedings of the KDD’16: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. https://doi.org/10.1145/2939672.2939785.
- 27.
Lundberg, S.M.; Lee, S.I. A Unified Approach to Interpreting Model Predictions. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; Volume 30, pp. 4765–4774.
- 28.
Guo, R.; Yang, B.; Guo, Y.; et al. Machine learning-based prediction of outdoor thermal comfort: Combining Bayesian optimization and the SHAP model. Build. Environ. 2024, 254, 111301. https://doi.org/10.1016/j.buildenv.2024.111301.
- 29.
Molnar, C.; König, G.; Herbinger, J.; et al. General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models. In xxAI—Beyond Explainable AI; Springer International Publishing: Cham, Switzerland, 2022; Volume 13200, pp. 39–68. https://doi.org/10.1007/978-3-031-04083-2_4.
- 30.
Aas, K.; Jullum, M.; Løland, A. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artif. Intell. 2021, 298, 103502. https://doi.org/10.1016/j.artint.2021.103502.
- 31.
Roberts, D.R.; Bahn, V.; Ciuti, S.; et al. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography 2017, 40, 913–929. https://doi.org/10.1111/ecog.02881.
- 32.
Fisher, N.I. Statistical Analysis of Circular Data; Cambridge University Press: Cambridge, UK, 1993. https://doi.org/10.1017/cbo9780511564345.
- 33.
Thom, E.C. The Discomfort Index. Weatherwise 1959, 12, 57–61. https://doi.org/10.1080/00431672.1959.9926960.
- 34.
Hollander, M.; Wolfe, D.A.; Chicken, E. Nonparametric Statistical Methods, 3rd ed.; Wiley: Hoboken, NJ, USA, 2015. https://doi.org/10.1002/9781119196037.
- 35.
Cerqueira, V.; Torgo, L.; Mozetič, I. Evaluating time series forecasting models: An empirical study on performance estimation methods. Mach. Learn. 2020, 109, 1997–2028. https://doi.org/10.1007/s10994-020-05910-7.
- 36.
Sweet, L.B.; Müller, C.; Anand, M.; et al. Cross-Validation Strategy Impacts the Performance and Interpretation of Machine Learning Models. Artif. Intell. Earth Syst. 2023, 2, e230026. https://doi.org/10.1175/aies-d-23-0026.1.
- 37.
Lundberg, S.M.; Erion, G.; Chen, H.; et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2020, 2, 56–67. https://doi.org/10.1038/s42256-019-0138-9.
- 38.
Cleveland, W.S. Robust Locally Weighted Regression and Smoothing Scatterplots. J. Am. Stat. Assoc. 1979, 74, 829–836. https://doi.org/10.1080/01621459.1979.10481038.
- 39.
Efron, B. Bootstrap Methods: Another Look at the Jackknife. Ann. Stat. 1979, 7, 1–26. https://doi.org/10.1214/aos/1176344552.
- 40.
Lahiri, S.N. Resampling Methods for Dependent Data; Springer: New York, NY, USA, 2003. https://doi.org/10.1007/978-1-4757-3803-2.
- 41.
Solanki, P.; Amirtham, L.R.; Deb, C. Optimizing sky view factor and vegetation to mitigate urban heat in hot-humid climates. Discov. Cities 2025, 2, 79. https://doi.org/10.1007/s44327-025-00108-9.
- 42.
Zhang, H.; Ao, M.; Ardabili, N.G.; et al. Impact of urban sunken square design on summer outdoor thermal comfort using machine learning. Urban Clim. 2024, 58, 102214. https://doi.org/10.1016/j.uclim.2024.102214.
- 43.
Mandić, L.; Đjukić, A.; Marić, J.; et al. A Systematic Review of Outdoor Thermal Comfort Studies for the Urban (Re)Design of City Squares. Sustainability 2024, 16, 4920. https://doi.org/10.3390/su16124920.
- 44.
Zhong, H.; Feng, J.; Lam, C.K.C.; et al. The impact of semi-open street roofs on urban pollutant exposure and pedestrian-level thermal comfort in 2-D street canyons. Build. Environ. 2023, 239, 110387. https://doi.org/10.1016/j.buildenv.2023.110387.
- 45.
Zou, J.; Yu, Y.; Liu, J.; et al. Field measurement of the urban pedestrian level wind turbulence. Build. Environ. 2021, 194, 107713. https://doi.org/10.1016/j.buildenv.2021.107713.
- 46.
Nasrollahi, N.; Namazi, Y.; Taleghani, M. The effect of urban shading and canyon geometry on outdoor thermal comfort in hot climates: A case study of Ahvaz, Iran. Sustain. Cities Soc. 2021, 65, 102638. https://doi.org/10.1016/j.scs.2020.102638.
- 47.
Zhou, Z.; Nguyen-Xuan, T.; Liao, H.; et al. Characterization of temperature and humidity effects on extreme heat stress under global warming and urban growth in the Pearl and Yangtze River Deltas of China. Weather Clim. Extrem. 2024, 44, 100659. https://doi.org/10.1016/j.wace.2024.100659.
- 48.
Li, Y.; Fei, W.; Yang, M.; et al. How to realize large-scale outdoor thermal comfort studies? A systematic review based on OTC characterization, methods and research trends. Front. Sustain. Cities 2025, 7, 1552994. https://doi.org/10.3389/frsc.2025.1552994.
- 49.
Jiang, J.; Li, Z.; Bedra, K.B.; et al. Predicting outdoor thermal comfort in traditional villages: An explainable machine learning framework integrating model optimization, seasonal variability, and tourist-resident insights. Build. Environ. 2025, 282, 113315. https://doi.org/10.1016/j.buildenv.2025.113315.
- 50.
Zhang, M.; Zhou, D.; Xu, D.; et al. How do built environment factors influence urban heat islands across local climate zones? Evidence from an interpretable XGBoost-SHAP model. Sustain. Cities Soc. 2026, 136, 107078. https://doi.org/10.1016/j.scs.2025.107078.
- 51.
Villaverde, A.; Álvarez, I.; Rojí, E.; et al. Categorisation of urban open spaces for heat adaptation: A cluster based approach. Build. Environ. 2024, 263, 111861. https://doi.org/10.1016/j.buildenv.2024.111861.
This work is licensed under a Creative Commons Attribution 4.0 International License.
